Since I've installed openmpi I cannot submit any job that uses cpus from
different machines.
### hostfile ###
lcbcpc02.epfl.ch slots=4 max-slots=4
lcbcpc04.epfl.ch slots=4 max-slots=4
### error message ###
[matteo@lcbcpc02 TEST]$ mpirun --hostfile ~matteo/hostfile -np 8
/home/mat
This is the ifconfig output from the machine I'm used to submit the
parallel job:
### ifconfig output - master node ###
[root@lcbcpc02 ~]# ifconfig
eth0 Link encap:Ethernet HWaddr 00:15:17:10:53:C8
inet addr:128.178.54.74 Bcast:128.178.54.255 Mask:255.255.255.0
inet6
Jeff Squyres wrote:
> On Feb 12, 2007, at 12:54 PM, Matteo Guglielmi wrote:
>
>
>> This is the ifconfig output from the machine I'm used to submit the
>> parallel job:
>>
>
> It looks like both of your nodes share an IP address:
>
>
>
Jeff Squyres wrote:
> On Feb 12, 2007, at 2:34 PM, Matteo Guglielmi wrote:
>
>
>> Those nic "eth1" are not connected at all... all the machines use
>> only the eth0
>> interface which have different IP for each PC.
>>
>
> Gotcha. But, FWI
unsubscribe
Matteo Guglielmi | DALCO AG | Industriestr. 28 | 8604 Volketswil | Switzerland
| T: +41 44 908 38 38 | D: +41 44 908 38 37
To unsubscribe from this group and stop receiving emails from it, send an email
to users+unsubscr...@lists.open-mpi.org.
I'm trying to get openmpi over RoCE working with this setup:
card: https://www.gigabyte.com/Accessory/CLNOQ42-rev-10#ov
OS: CentOS 7.7
modinfo qede
filename:
/lib/modules/3.10.0-1062.4.1.el7.x86_64/kernel/drivers/net/ethernet/qlogic/qede/qede.ko.xz
version:8.37.0.20
license:
version should be 8.37.7.0
will now try to upgrade the firmware since changing OS is not an option.
Other suggestions?
Thank you!
From: Llolsten Kaonga
Sent: Wednesday, November 13, 2019 3:25:16 PM
To: 'Open MPI Users'
Cc: Matteo Guglielmi
S
er 13, 2019 7:16:41 PM
To: Open MPI User's List
Cc: Llolsten Kaonga; Matteo Guglielmi
Subject: Re: [OMPI users] qelr_alloc_context: Failed to allocate context for
device.
Have you tried using the UCX PML?
The UCX PML is Mellanox's preferred Open MPI mechanism (instead of using the
openib B
Sent: Wednesday, November 13, 2019 3:25:16 PM
To: 'Open MPI Users'
Cc: Matteo Guglielmi
Subject: RE: [OMPI users] qelr_alloc_context: Failed to allocate context for
device.
Hello Mateo,
What version of openmpi are you running?
Also, the OFED-4.17-1 release notes do not claim support
